Unified analysis on multistablity of fraction-order multidimensional-valued memristive neural networks.
Neural Netw
; 179: 106498, 2024 Nov.
Article
em En
| MEDLINE
| ID: mdl-38986183
ABSTRACT
This article provides a unified analysis of the multistability of fraction-order multidimensional-valued memristive neural networks (FOMVMNNs) with unbounded time-varying delays. Firstly, based on the knowledge of fractional differentiation and memristors, a unified model is established. This model is a unified form of real-valued, complex-valued, and quaternion-valued systems. Then, based on a unified method, the number of equilibrium points for FOMVMNNs is discussed. The sufficient conditions for determining the number of equilibrium points have been obtained. By using 1-norm to construct Lyapunov functions, the unified criteria for multistability of FOMVMNNs are obtained, these criteria are less conservative and easier to verify. Moreover, the attraction basins of the stable equilibrium points are estimated. Finally, two numerical simulation examples are provided to verify the correctness of the results.
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Simulação por Computador
/
Redes Neurais de Computação
Idioma:
En
Ano de publicação:
2024
Tipo de documento:
Article